Security Guard — Security agent for Claude Code
Security audit of financial code.
How to install Security Guard
Installs to ~/.claude/agents/sergeeey-claude-cod-top-2026-security-guard.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/sergeeey/Claude-cod-top-2026/HEAD/agents/security-guard.md -o ~/.claude/agents/sergeeey-claude-cod-top-2026-security-guard.md Restart Claude Code, or start a new session, for it to be picked up.
What Security Guard does
name: security-guard description: Security audit of financial code. Invoke before a release or when working with sensitive data. tools: Read, Grep, Glob, Bash model: opus maxTurns: 10 memory: project effort: high skills: [security-audit] whenToUse: "Before any production release or when auditing financial/auth code for security vulnerabilities"
You are an information security specialist for financial systems. Domain: financial applications, regulatory compliance.
Before the audit:
- **
Alternatives in Security
- Beads Warden — Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write ra 2.7k ★
- Review Security — Reviews code changes for security vulnerabilities including injection attacks, sensitive data exposure, insecu 432 ★
- Dashclaw Security Reviewer — Read-only security reviewer specialized for the DashClaw stack (Next.js 16 App Router, Neon/Postgres via repos 297 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Security Agent.Agent
Use when a change touches permissions, authentication, dependencies, configuration, release surfaces, sensitiv
Security Fixer
Implement the minimal fix for a confirmed security finding with a working PoC. Creates a branch, edits source
Craft Code Reviewer Deep
Deep code review on Opus 4.8 for high-stakes PRs — release branches, security-sensitive code, large architectu
Deep Audit
Thorough code review for correctness, security, and quality. Use this agent before releases, after security-se
Ship Lead
Release engineer and QA lead combined. Summon before any deployment to run a comprehensive production-readines
Safeguard
Security audit specialist. Use proactively before release, after touching auth, payments, file upload, or user
Related Skills
Claude Guard Hook
A global Claude Code hook that intercepts sensitive data before it reaches the LLM — secrets, API keys, PII, a
Create Hook Dtd
Invoke create-hooks-dtd for a hook whose payload is data and whose guard is tripped before it ships
Sensitive Canary
Claude Code hooks that guard secrets and PII before they reach the Anthropic API